Axiomatic Approach to Feature Subset Selection Based on Relevance

  • Authors:
  • Hui Wang;David Bell;Fionn Murtagh

  • Affiliations:
  • Univ. of Ulster, Northern Ireland, UK;Univ. of Ulster, Northern Ireland, UK;Univ. of Ulster, Northern Ireland, UK

  • Venue:
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Year:
  • 1999

Quantified Score

Hi-index 0.15

Visualization

Abstract

Relevance has traditionally been linked with feature subset selection, but formalization of this link has not been attempted. In this paper, we propose two axioms for feature subset selection驴sufficiency axiom and necessity axiom驴based on which this link is formalized: The expected feature subset is the one which maximizes relevance. Finding the expected feature subset turns out to be NP-hard. We then devise a heuristic algorithm to find the expected subset which has a polynomial time complexity. The experimental results show that the algorithm finds good enough subset of features which, when presented to C4.5, results in better prediction accuracy.